Metadata-Version: 2.4
Name: omniuq
Version: 0.1.0
Summary: Simple uncertainty quantification and language model utilities.
Author: Mina Gabriel
License: MIT
Project-URL: Homepage, https://github.com/MinaGabriel/omniuq
Project-URL: Repository, https://github.com/MinaGabriel/omniuq
Project-URL: Issues, https://github.com/MinaGabriel/omniuq/issues
Keywords: llm,language-models,uncertainty,question-answering,transformers,huggingface
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: torch>=2.0
Requires-Dist: transformers>=4.40
Requires-Dist: accelerate>=0.28
Provides-Extra: dev
Requires-Dist: pytest>=8.0; extra == "dev"
Requires-Dist: build>=1.2; extra == "dev"
Requires-Dist: twine>=5.0; extra == "dev"
Dynamic: license-file

# OMNI-QU
omniuq is a modular Python toolkit for quantifying and decomposing uncertainty in LLM responses. One interface, many methods.
